基于分批试验的工业球磨机粒级分布预测模型  

Particle Size Distribution Predictive Model of Industrial Ball Mill Based on Batch Grinding Experiment

作　　者：马天雨[1] 桂卫华[1] 王雅琳[1] 阳春华[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083

出　　处：《北京工业大学学报》2012年第9期1281-1286,共6页Journal of Beijing University of Technology

基　　金：国家自然科学基金重点资助项目(61134006)

摘　　要：针对具有强非线性、时滞和工况变化特点的球磨机出口矿浆粒级分布预测问题,提出一种基于分批试验结论的粒级质量平衡改进模型.根据某些粒级的矿料不符合一阶破碎动力学的分批试验结论改进了破碎率模型;考虑工况影响,建立了模型参数和工况变量间的最小二乘支持向量机(LSSVM)关系模型,由现场工况确定模型参数.仿真结果表明,该模型预测精度较高,可满足实际生产要求.An improved size-mass balance model based on batch-grinding experiment was proposed to predict the particle size distribution of industrial ball mill, which had the characteristics of high nonlinearity, time-delay and operation conditions changing. The breakage-rate model was improved based on the batch-grinding results that some certain size particles did not meet first-order breakage kinetics. Considered the influence of operating conditions, a LSSVM model between the parameters of the ball-mil model and the operating conditions was trained, so that the parameters of breakage rate model could be determined by grinding conditions. Simulation results show that the accuracy of this model is good enough and meets the needs of practical production.

关 键 词：一阶破碎动力学 粒级质量平衡 最小二乘支持向量机 磨矿过程 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]